linux-kernel - Re: [PATCH 5/6] tracing, documentation: Add a document describing how to do some performance analysis with tracepoints

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:	Fri, 7 Aug 2009 15:25:35 +0100
From:	Mel Gorman <mel@....ul.ie>
To:	Ingo Molnar <mingo@...e.hu>
Cc:	Fr?d?ric Weisbecker <fweisbec@...il.com>,
	Pekka Enberg <penberg@...helsinki.fi>, eduard@...e.hu,
	Larry Woodman <lwoodman@...hat.com>,
	Andrew Morton <akpm@...ux-foundation.org>, riel@...hat.com,
	Peter Zijlstra <peterz@...radead.org>,
	LKML <linux-kernel@...r.kernel.org>, linux-mm@...ck.org
Subject: Re: [PATCH 5/6] tracing, documentation: Add a document describing
	how to do some performance analysis with tracepoints

On Fri, Aug 07, 2009 at 10:07:07AM +0200, Ingo Molnar wrote:
> > <SNIP>
> 
> This is a very nice and comprehensive description!
> 

Thanks, you did write a nice chunk of it yourself though :)

> I'm wondering: would you mind if we integrated the analysis ideas 
> from your perl script into 'perf trace'? Those kinds of high-level 
> counts and summaries are useful not just for MM events.
> 

Of course not. Part of the motivation for doing the perl script was as a
POC for the gathering of high-level events. In the event such sample
scripts work out, it'd justify the greater effort to integrate them into
perf.

> Another thing that was raise dbefore is a 'perf mem' special-purpose 
> tool to help the analysis of all things memory related: leak 
> detection, high level stats, etc. That could have some turn-key 
> modes of analysis for the page allocator too.
> 

Again, my vague notion was to prototype such things in perl and then when it
works out to incorporate it in perf if suitable. As high-level gathering of
information is just a state machine, it's conceivable that some of the code
could be auto-generated.

> perf will do a proper format-string evaluation of 
> /debug/tracing/events/*/format as well, thus any tweaks to the 
> tracepoints get automatically adopted to.
> 

Which would be a major plus.

-- 
Mel Gorman
Part-time Phd Student                          Linux Technology Center
University of Limerick                         IBM Dublin Software Lab
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/